AI agents use update_flow_js_block to create or update resources in Nocobase — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Nocobase environment.
This is a Write operation because it modifies (updates) existing JavaScript block code. It is not Destructive because the change is reversible (can be updated again). It is not Execute because the tool itself doesn't run the code—it only stores/modifies the code definition.
From the tool's definition Tool description states 'Update the JavaScript code of a JSBlockModel' — this modifies code that executes in the NocoBase sandbox. The example shows ctx.render() which executes arbitrary JavaScript within a sandboxed environment.
Attacks that exploit this kind of access
Update the JavaScript code of a JSBlockModel inside a flowPage. Code runs in NocoBase sandbox — use ctx.render(htmlString) to render output. Example: ctx.render(. It is categorised as a Write tool in the Nocobase MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Nocobase MCP server in PolicyLayer and add a rule for update_flow_js_block: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Nocobase. Nothing to install.
update_flow_js_block is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update_flow_js_block rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for update_flow_js_block. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
update_flow_js_block is provided by the Nocobase MCP server (puguhsudarma/nocobase-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →